Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/wittyreference/twilio-claude-plugin/pushgit clone --depth 1 https://github.com/wittyreference/twilio-claude-pluginWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00022 | $0.00859 |
| Opus 5 | $0.00011 | $0.00430 |
| Sonnet 5 | $0.00004 | $0.00172 |
| Haiku 4.5 | $0.00002 | $0.00086 |
Grade A, and why
push scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Push via Pull Request
Push changes to remote through a PR workflow. Never pushes directly to main — always creates a PR, waits for CI, and merges.
Pre-Push Checks
Run these checks before pushing. Stop and report if any fail.
1. Uncommitted Changes
git status
If there are uncommitted changes, warn the user and suggest /commit first.
2. Test Suite
npm test
All tests must pass before pushing.
3. gh CLI
Verify gh is installed and authenticated:
gh auth status
If not authenticated, tell the user to run ! gh auth login.
Determine Push Strategy
Check the current branch and unpushed commits:
BRANCH=$(git branch --show-current)
git fetch origin main
UNPUSHED=$(git log --oneline origin/main..HEAD)
If on main with unpushed commits
- Show the commits and ask the user: push all as one PR (default), or specify a subset?
- Create PR branch from
origin/main:
Branch naming: derive from commit messages using conventional format (git checkout -b <branch-name> origin/main git cherry-pick <commit1> <commit2> ...feat/thing,fix/thing,docs/thing). For mixed types, use the dominant one. - Push the branch:
git push -u origin <branch-name> - Switch back to main:
git checkout main - Continue to Create PR below.
If on a feature/worktree branch
- Push the branch:
git push -u origin <branch-name> - Check for existing PR:
If a PR already exists and is open, skip to Wait for CI.gh pr view --json number,state 2>/dev/null - Continue to Create PR below.
If no unpushed commits
Report "Nothing to push" and stop.
Create PR
Generate a PR title and body from the commits:
gh pr create \
--title "<title>" \
--body "<body>" \
--base main
Title: For 1-commit PRs, use the commit message. For multi-commit, write a summary in conventional commit style.
Body: Include:
## What— brief description of changes## Why— motivation (derive from commit messages)- Commit list if multi-commit
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 145 lines · 22 tokens per session scan A 63136d192402
push is a command published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 859 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.